Related Experiment Video
Updated: Nov 1, 2025
08:05
Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia
Published on: December 19, 2020
14.4K
Dense GAN and multi-layer attention based lesion segmentation method for COVID-19 CT images
Ju Zhang1, Lundun Yu2, Decheng Chen2
1Zhijiang College of Zhejiang University of Technology, Shaoxing 312030, China.
Biomedical Signal Processing and Control
|June 28, 2021
Summary
This study introduces a novel deep learning method for segmenting COVID-19 lung lesions in CT scans. The approach enhances segmentation accuracy, aiding in patient screening and diagnosis.
Area of Science:
- Medical Imaging
- Artificial Intelligence
- Pulmonology
Background:
- The global spread of COVID-19 necessitates efficient diagnostic tools.
- CT imaging is crucial for identifying lung lesions in COVID-19 patients.
- Accurate segmentation of lung lesions is vital for diagnosis and treatment planning.
Purpose of the Study:
- To address challenges in deep learning-based segmentation of COVID-19 lung lesions.
- To improve the accuracy of segmenting COVID-19 pulmonary CT images.
- To develop a method that assists radiologists in patient screening and diagnosis.
Main Methods:
- Development of an improved Dense Generative Adversarial Network (GAN) for dataset expansion.
- Implementation of a multi-layer attention mechanism.
- Integration with the U-Net architecture for COVID-19 pulmonary CT image segmentation.
Main Results:
- The proposed method demonstrated improved segmentation accuracy for COVID-19 pulmonary CT images.
- Experimental results showed superior performance compared to existing image segmentation methods.
- The enhanced dataset and attention mechanism contributed to better lesion identification.
Conclusions:
- The developed deep learning model effectively segments COVID-19 lung lesions in CT scans.
- This method offers a promising tool for improving diagnostic accuracy and efficiency.
- The approach can aid in the screening and management of COVID-19 patients.
